Skip to content
Skills Library
Security · Building & coding

security

/security

Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.

Repository
llms ↗
Licence
MIT
Last repository change
21.05.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
13
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 21.05.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.

Triggers from the description

how do I secure thissecurity best practicesis this secureharden this
Original author description

Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.

How it works

  1. Usage
  2. Workflow
  3. Template Locations
  4. Progressive Disclosure Rules
  5. Examples
Original SKILL.md headings · 117 lines, 499 words
SKILL.md preview
---
name: security
description: Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.
allowed-tools: Read, Grep, Glob, Bash
---

# Security — Implementation SOPs

Unified security guidance for your stack. Auto-detects context from edited files or accepts explicit mode.

## Usage

```
/security                     # Auto-detect stack from git changes
/security backend             # Explicit: FastAPI + SQLAlchemy + Redis
/security frontend            # Explicit: Jinja2 + HTMX + TypeScript/Vite
/security database            # Explicit: PostgreSQL + pgvector + Redis
/security infrastructure      # Explicit: Docker + Nginx + Cloudflare
/security operations          # Explicit: Deployment + secrets + monitoring
/security matrix              # Cross-reference matrix (L1/L2/L3)
/security checklist           # L1 essential pre-deployment checklist
```

## Workflow

### Step 1: Determine Context

Parse `$ARGUMENTS` for explicit mode. If no arguments provided, detect context:

```bash
DETECTED=$(bash "$HOME/.claude/skills/security/lib/context-detector.sh")
```

### Step 2: Show Relevant Guidance

Based on detected or explicit mode, use progressive disclosure:

**Level 1 — Summary** (default, ~10 lines):
Show the summary template for the detected stack. This is the entry point.

**Level 2 — Patterns** (on request, ~50 lines):
When user asks for more detail, patterns, or "Don't/Do/Best" examples, show the patterns template.

**Level 3 — Full SOP** (on request, ~500-1100 lines):
When user asks for the complete SOP, read the full source skill file.

### Step 3: Handle Multiple Stacks

If context-detector returns multiple stacks (e.g., "backend,frontend"):

- Show summary for each detected stack
- Let user choose which to dive deeper into

### Step 4: No Context Detected

If detection returns "none" and no explicit mode:

- Show the matrix template as overview
- List available modes for user to choose

## Template Locations

### Summary Templates (~10 lines each)

| Mode           | File                                                            |
| -------------- | --------------------------------------------------------------- |
| backend        | `~/.claude/skills/security/templates/backend/summary.md`        |
| frontend       | `~/.claude/skills/security/templates/frontend/summary.md`       |
| database       | `~/.claude/skills/security/templates/database/summary.md`       |
| infrastructure | `~/.claude/skills/security/templates/infrastructure/summary.md` |
| operations     | `~/.claude/skills/security/templates/operations/summary.md`     |

### Patterns Templates (~50 lines each, Don't/Do/Best)

| Mode           | File                                                             |
| -------------- | ---------------------------------------------------------------- |
| backend        | `~/.claude/skills/security/templates/backend/patterns.md`        |
| frontend       | `~/.claude/skills/security/templates/frontend/patterns.md`       |
| database       | `~/.claude/skills/security/templates/database/patterns.md`       |
| infrastructure | `~/.claude/skills/security/templates/infrastructure/patterns.md` |
| operations     | `~/.claude/skills/security/templates/operations/patterns.md`     |

### Reference Templates

| Mode      | File                                               |
| --------- | -------------------------------------------------- |
| matrix    | `~/.claude/skills/security/templates/matrix.md`    |
| checklist | `~/.claude/skills/security/templates/checklist.md` |

## Progressive Disclosure Rules

1. **Always start with summary** — don't dump 1,100 lines unprompted
2. **Read templates on demand** — use the Read tool to load templates, don't memorize content
3. **User drives depth** — "show patterns", "full SOP", "show me the code" trigger deeper levels
4. **Combine when relevant** — if user edits both .py and Dockerfile, show both backend + infrastructure summaries

## Examples

**Auto-detected backend work:**

> User edited `src/auth.py`
> → context-detector returns "backend"
> → Read and show `templates/backend/summary.md`
> → User: "show me password hashing patterns"
> → Read and show `templates/backend/patterns.md`

**Explicit infrastructure request:**

> User: `/security infrastructure`
> → Read and show `templates/infrastructure/summary.md`

**No context, overview requested:**

> User: `/security`
> → context-detector returns "none"
> → Read and show `templates/matrix.md`

**Pre-deployment check:**

> User: `/security checklist`
> → Read and show `templates/checklist.md`
Files in this package (13)
  • SKILL.md 5 KB
  • templates/checklist.md 4 KB
  • templates/matrix.md 7 KB
  • templates/backend/patterns.md 2 KB
  • templates/backend/summary.md 1 KB
  • templates/database/patterns.md 2 KB
  • templates/database/summary.md 1 KB
  • templates/frontend/patterns.md 2 KB
  • templates/frontend/summary.md 1 KB
  • templates/infrastructure/patterns.md 2 KB
  • templates/infrastructure/summary.md 1 KB
  • templates/operations/patterns.md 2 KB
  • templates/operations/summary.md 1 KB

Versions

RepositoryScoreLicence
This page · matteocervelli/llms100MIT
flavien-ia/hypervibe-craft100Apache-2.0
boshu2/agentops100Apache-2.0
iamalisson/landspec100MIT
asckye/tia_portal_openness_mcp100MIT
Esposter/Esposter100Apache-2.0
event4u-app/agent-config100MIT
motormetrics/motormetrics100MIT
motormetrics/motormetrics100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version ccb9d1002d3d (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90security-reactnative
    Security - React Native 0.87 Best Practices. Use when reviewing security, implementing auth, or hardening code.
  • 86skill-086
    Use when working with security scanning security hardening
  • 100linear-security-basics
    Secure API key management and OAuth best practices for Linear. Use when setting up authentication securely, implementing OAuth flows, or hardening Linear integrations. Trigger with phrases like "linear security", "linear API key security", "linear OAuth", "secure linear…
  • 100secure-software-engineering
    Use when designing or implementing software securely: define security requirements, threat-model a feature, choose secure defaults, design authentication and authorization, handle untrusted data and secrets, evaluate dependencies, design multi-tenant trust boundaries, or review…
  • 90security-best-practices
    Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages…
  • 90security-best-practices
    Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.